We show that classifiers trained with random region proposals achieve state-of-the-art Open-world Object Detection (OWOD): they can not only maintain the accuracy of the known objects (w/ training labels), but also considerably improve the recall of unknown ones (w/o training labels). Specifically, we propose RandBox, a Fast R-CNN based architecture trained on random proposals at each training iteration, surpassing existing Faster R-CNN and Transformer based OWOD. Its effectiveness stems from the following two benefits introduced by randomness. First, as the randomization is independent of the distribution of the limited known objects, the random proposals become the instrumental variable that prevents the training from being confounded by the known objects. Second, the unbiased training encourages more proposal explorations by using our proposed matching score that does not penalize the random proposals whose prediction scores do not match the known objects. On two benchmarks: Pascal-VOC/MS-COCO and LVIS, RandBox significantly outperforms the previous state-of-the-art in all metrics. We also detail the ablations on randomization and loss designs. Codes are available at https://github.com/scuwyh2000/RandBox.
We analyze the DETR-based framework on semi-supervised object detection (SSOD) and observe that (1) the one-to-one assignment strategy generates incorrect matching when the pseudo ground-truth bounding box is inaccurate, leading to training inefficiency; (2) DETR-based detectors lack deterministic correspondence between the input query and its prediction output, which hinders the applicability of the consistency-based regularization widely used in current SSOD methods. We present Semi-DETR, the first transformer-based end-to-end semi-supervised object detector, to tackle these problems. Specifically, we propose a Stage-wise Hybrid Matching strategy that combines the one-to-many assignment and one-to-one assignment strategies to improve the training efficiency of the first stage and thus provide high-quality pseudo labels for the training of the second stage. Besides, we introduce a Crossview Query Consistency method to learn the semantic feature invariance of object queries from different views while avoiding the need to find deterministic query correspondence. Furthermore, we propose a Cost-based Pseudo Label Mining module to dynamically mine more pseudo boxes based on the matching cost of pseudo ground truth bounding boxes for consistency training. Extensive experiments on all SSOD settings of both COCO and Pascal VOC benchmark datasets show that our Semi-DETR method outperforms all state-of-the-art methods by clear margins. The PaddlePaddle version code1 is at https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/semi_det/semi_detr.
Recent work in unsupervised multi-object segmentation shows impressive results by predicting motion from a single image despite the inherent ambiguity in predicting motion without the next image. On the other hand, the set of possible motions for an image can be constrained to a low-dimensional space by considering the scene structure and moving objects in it. We propose to model pixel-wise geometry and object motion to remove ambiguity in reconstructing flow from a single image. Specifically, we divide the image into coherently moving regions and use depth to construct flow bases that best explain the observed flow in each region. We achieve state-of-the-art results in unsupervised multi-object segmentation on synthetic and real-world datasets by modeling the scene structure and object motion. Our evaluation of the predicted depth maps shows reliable performance in monocular depth estimation.
Semantic scene completion (SSC) requires an accurate understanding of the geometric and semantic relationships between the objects in the 3D scene for reasoning the occluded objects. The popular SSC methods voxelize the 3D objects, allowing the deep 3D convolutional network (3D CNN) to learn the object relationships from the complex scenes. However, the current networks lack the controllable kernels to model the object relationship across multiple views, where appropriate views provide the relevant information for suggesting the existence of the occluded objects. In this paper, we propose Cross-View Synthesis Transformer (CVSformer), which consists of Multi-View Feature Synthesis and Cross-View Transformer for learning cross-view object relationships. In the multi-view feature synthesis, we use a set of 3D convolutional kernels rotated differently to compute the multi-view features for each voxel. In the cross-view transformer, we employ the cross-view fusion to comprehensively learn the cross-view relationships, which form useful information for enhancing the features of individual views. We use the enhanced features to predict the geometric occupancies and semantic labels of all voxels. We evaluate CVSformer on public datasets, where CVSformer yields state-of-the-art results.
Bounding box regression (BBR) has been widely used in object detection and instance segmentation, which is an important step in object localization. However, most of the existing loss functions for bounding box regression cannot be optimized when the predicted box has the same aspect ratio as the groundtruth box, but the width and height values are exactly different. In order to tackle the issues mentioned above, we fully explore the geometric features of horizontal rectangle and propose a novel bounding box similarity comparison metric MPDIoU based on minimum point distance, which contains all of the relevant factors considered in the existing loss functions, namely overlapping or non-overlapping area, central points distance, and deviation of width and height, while simplifying the calculation process. On this basis, we propose a bounding box regression loss function based on MPDIoU, called LMPDIoU . Experimental results show that the MPDIoU loss function is applied to state-of-the-art instance segmentation (e.g., YOLACT) and object detection (e.g., YOLOv7) model trained on PASCAL VOC, MS COCO, and IIIT5k outperforms existing loss functions.
We aim to investigate whether end-to-end learning of visual reasoning can be achieved with general-purpose neural networks, with the help of visual pretraining. A positive result would refute the common belief that explicit visual abstraction (e.g. object detection) is essential for compositional generalization on visual reasoning, and confirm the feasibility of a neural network "generalist" to solve visual recognition and reasoning tasks. We propose a simple and general self-supervised framework which "compresses" each video frame into a small set of tokens with a transformer network, and reconstructs the remaining frames based on the compressed temporal context. To minimize the reconstruction loss, the network must learn a compact representation for each image, as well as capture temporal dynamics and object permanence from temporal context. We perform evaluation on two visual reasoning benchmarks, CATER and ACRE. We observe that pretraining is essential to achieve compositional generalization for end-to-end visual reasoning. Our proposed framework outperforms traditional supervised pretraining, including image classification and explicit object detection, by large margins.
Accurate and robust object detection is critical for autonomous driving. Image-based detectors face difficulties caused by low visibility in adverse weather conditions. Thus, radar-camera fusion is of particular interest but presents challenges in optimally fusing heterogeneous data sources. To approach this issue, we propose two new radar preprocessing techniques to better align radar and camera data. In addition, we introduce a Multi-Task Cross-Modality Attention-Fusion Network (MCAF-Net) for object detection, which includes two new fusion blocks. These allow for exploiting information from the feature maps more comprehensively. The proposed algorithm jointly detects objects and segments free space, which guides the model to focus on the more relevant part of the scene, namely, the occupied space. Our approach outperforms current state-of-the-art radar-camera fusion-based object detectors in the nuScenes dataset and achieves more robust results in adverse weather conditions and nighttime scenarios.
Radars, due to their robustness to adverse weather conditions and ability to measure object motions, have served in autonomous driving and intelligent agents for years. However, Radar-based perception suffers from its unintuitive sensing data, which lack of semantic and structural information of scenes. To tackle this problem, camera and Radar sensor fusion has been investigated as a trending strategy with low cost, high reliability and strong maintenance. While most recent works explore how to explore Radar point clouds and images, rich contextual information within Radar observation are discarded. In this paper, we propose a hybrid point-wise Radar-Optical fusion approach for object detection in autonomous driving scenarios. The framework benefits from dense contextual information from both the range-doppler spectrum and images which are integrated to learn a multi-modal feature representation. Furthermore, we propose a novel local coordinate formulation, tackling the object detection task in an object-centric coordinate. Extensive results show that with the information gained from optical images, we could achieve leading performance in object detection (97.69\% recall) compared to recent state-of-the-art methods FFT-RadNet (82.86\% recall). Ablation studies verify the key design choices and practicability of our approach given machine generated imperfect detections. The code will be available at https://github.com/LiuLiu-55/ROFusion.
Vision-language (VL) Pre-training (VLP) has shown to well generalize VL models over a wide range of VL downstream tasks, especially for cross-modal retrieval. However, it hinges on a huge amount of image-text pairs, which requires tedious and costly curation. On the contrary, weakly-supervised VLP (W-VLP) explores means with object tags generated by a pre-trained object detector (OD) from images. Yet, they still require paired information, i.e. images and object-level annotations, as supervision to train an OD. To further reduce the amount of supervision, we propose Prompts-in-The-Loop (PiTL) that prompts knowledge from large language models (LLMs) to describe images. Concretely, given a category label of an image, e.g. refinery, the knowledge, e.g. a refinery could be seen with large storage tanks, pipework, and ..., extracted by LLMs is used as the language counterpart. The knowledge supplements, e.g. the common relations among entities most likely appearing in a scene. We create IN14K, a new VL dataset of 9M images and 1M descriptions of 14K categories from ImageNet21K with PiTL. Empirically, the VL models pre-trained with PiTL-generated pairs are strongly favored over other W-VLP works on image-to-text (I2T) and text-to-image (T2I) retrieval tasks, with less supervision. The results reveal the effectiveness of PiTL-generated pairs for VLP.
This paper describes a domestic service robot (DSR) that fetches everyday objects and carries them to specified destinations according to free-form natural language instructions. Given an instruction such as "Move the bottle on the left side of the plate to the empty chair," the DSR is expected to identify the bottle and the chair from multiple candidates in the environment and carry the target object to the destination. Most of the existing multimodal language understanding methods are impractical in terms of computational complexity because they require inferences for all combinations of target object candidates and destination candidates. We propose Switching Head-Tail Funnel UNITER, which solves the task by predicting the target object and the destination individually using a single model. Our method is validated on a newly-built dataset consisting of object manipulation instructions and semi photo-realistic images captured in a standard Embodied AI simulator. The results show that our method outperforms the baseline method in terms of language comprehension accuracy. Furthermore, we conduct physical experiments in which a DSR delivers standardized everyday objects in a standardized domestic environment as requested by instructions with referring expressions. The experimental results show that the object grasping and placing actions are achieved with success rates of more than 90%.
Object-centric representations enable autonomous driving algorithms to reason about interactions between many independent agents and scene features. Traditionally these representations have been obtained via supervised learning, but this decouples perception from the downstream driving task and could harm generalization. In this work we adapt a self-supervised object-centric vision model to perform object decomposition using only RGB video and the pose of the vehicle as inputs. We demonstrate that our method obtains promising results on the Waymo Open perception dataset. While object mask quality lags behind supervised methods or alternatives that use more privileged information, we find that our model is capable of learning a representation that fuses multiple camera viewpoints over time and successfully tracks many vehicles and pedestrians in the dataset. Code for our model is available at https://github.com/wayveai/SOCS.
Measurement-adaptive track initiation remains a critical design requirement of many practical multi-target tracking systems. For labeled random finite sets multi-object filters, prior work has been established to construct a labeled multi-object birth density using measurements from multiple sensors. A truncation procedure has also been provided that leverages a stochastic Gibbs sampler to truncate the birth density for scalability. In this work, we introduce a deterministic herded Gibbs sampling truncation solution for efficient multi-sensor adaptive track initialization. Removing the stochastic behavior of the track initialization procedure without impacting average tracking performance enables a more robust tracking solution more suitable for safety-critical applications. Simulation results for linear sensing scenarios are provided to verify performance.
Object detection in remote sensing is a crucial computer vision task that has seen significant advancements with deep learning techniques. However, most existing works in this area focus on the use of generic object detection and do not leverage the potential of multimodal data fusion. In this paper, we present a comparison of methods for multimodal object detection in remote sensing, survey available multimodal datasets suitable for evaluation, and discuss future directions.
In the realm of Tiny AI, we introduce ``You Only Look at Interested Cells" (YOLIC), an efficient method for object localization and classification on edge devices. Through seamlessly blending the strengths of semantic segmentation and object detection, YOLIC offers superior computational efficiency and precision. By adopting Cells of Interest for classification instead of individual pixels, YOLIC encapsulates relevant information, reduces computational load, and enables rough object shape inference. Importantly, the need for bounding box regression is obviated, as YOLIC capitalizes on the predetermined cell configuration that provides information about potential object location, size, and shape. To tackle the issue of single-label classification limitations, a multi-label classification approach is applied to each cell for effectively recognizing overlapping or closely situated objects. This paper presents extensive experiments on multiple datasets to demonstrate that YOLIC achieves detection performance comparable to the state-of-the-art YOLO algorithms while surpassing in speed, exceeding 30fps on a Raspberry Pi 4B CPU. All resources related to this study, including datasets, cell designer, image annotation tool, and source code, have been made publicly available on our project website at https://kai3316.github.io/yolic.github.io
We propose a conceptually simple and thus fast multi-object tracking (MOT) model that does not require any attached modules, such as the Kalman filter, Hungarian algorithm, transformer blocks, or graph networks. Conventional MOT models are built upon the multi-step modules listed above, and thus the computational cost is high. Our proposed end-to-end MOT model, \textit{TicrossNet}, is composed of a base detector and a cross-attention module only. As a result, the overhead of tracking does not increase significantly even when the number of instances ($N_t$) increases. We show that TicrossNet runs \textit{in real-time}; specifically, it achieves 32.6 FPS on MOT17 and 31.0 FPS on MOT20 (Tesla V100), which includes as many as $>$100 instances per frame. We also demonstrate that TicrossNet is robust to $N_t$; thus, it does not have to change the size of the base detector, depending on $N_t$, as is often done by other models for real-time processing.
Understanding comprehensive assembly knowledge from videos is critical for futuristic ultra-intelligent industry. To enable technological breakthrough, we present HA-ViD - the first human assembly video dataset that features representative industrial assembly scenarios, natural procedural knowledge acquisition process, and consistent human-robot shared annotations. Specifically, HA-ViD captures diverse collaboration patterns of real-world assembly, natural human behaviors and learning progression during assembly, and granulate action annotations to subject, action verb, manipulated object, target object, and tool. We provide 3222 multi-view, multi-modality videos (each video contains one assembly task), 1.5M frames, 96K temporal labels and 2M spatial labels. We benchmark four foundational video understanding tasks: action recognition, action segmentation, object detection and multi-object tracking. Importantly, we analyze their performance for comprehending knowledge in assembly progress, process efficiency, task collaboration, skill parameters and human intention. Details of HA-ViD is available at: https://iai-hrc.github.io/ha-vid.
Existing object-search approaches enable robots to search through free pathways, however, robots operating in unstructured human-centered environments frequently also have to manipulate the environment to their needs. In this work, we introduce a novel interactive multi-object search task in which a robot has to open doors to navigate rooms and search inside cabinets and drawers to find target objects. These new challenges require combining manipulation and navigation skills in unexplored environments. We present HIMOS, a hierarchical reinforcement learning approach that learns to compose exploration, navigation, and manipulation skills. To achieve this, we design an abstract high-level action space around a semantic map memory and leverage the explored environment as instance navigation points. We perform extensive experiments in simulation and the real world that demonstrate that, with accurate perception, the decision making of HIMOS effectively transfers to new environments in a zero-shot manner. It shows robustness to unseen subpolicies, failures in their execution, and different robot kinematics. These capabilities open the door to a wide range of downstream tasks across embodied AI and real-world use cases.
Real-time object detection plays a vital role in various computer vision applications. However, deploying real-time object detectors on resource-constrained platforms poses challenges due to high computational and memory requirements. This paper describes a low-bit quantization method to build a highly efficient one-stage detector, dubbed as Q-YOLO, which can effectively address the performance degradation problem caused by activation distribution imbalance in traditional quantized YOLO models. Q-YOLO introduces a fully end-to-end Post-Training Quantization (PTQ) pipeline with a well-designed Unilateral Histogram-based (UH) activation quantization scheme, which determines the maximum truncation values through histogram analysis by minimizing the Mean Squared Error (MSE) quantization errors. Extensive experiments on the COCO dataset demonstrate the effectiveness of Q-YOLO, outperforming other PTQ methods while achieving a more favorable balance between accuracy and computational cost. This research contributes to advancing the efficient deployment of object detection models on resource-limited edge devices, enabling real-time detection with reduced computational and memory overhead.
In this paper, we explore the potential of Vision-Language Models (VLMs), specifically CLIP, in predicting visual object relationships, which involves interpreting visual features from images into language-based relations. Current state-of-the-art methods use complex graphical models that utilize language cues and visual features to address this challenge. We hypothesize that the strong language priors in CLIP embeddings can simplify these graphical models paving for a simpler approach. We adopt the UVTransE relation prediction framework, which learns the relation as a translational embedding with subject, object, and union box embeddings from a scene. We systematically explore the design of CLIP-based subject, object, and union-box representations within the UVTransE framework and propose CREPE (CLIP Representation Enhanced Predicate Estimation). CREPE utilizes text-based representations for all three bounding boxes and introduces a novel contrastive training strategy to automatically infer the text prompt for union-box. Our approach achieves state-of-the-art performance in predicate estimation, mR@5 27.79, and mR@20 31.95 on the Visual Genome benchmark, achieving a 15.3\% gain in performance over recent state-of-the-art at mR@20. This work demonstrates CLIP's effectiveness in object relation prediction and encourages further research on VLMs in this challenging domain.
Transparent objects are encountered frequently in our daily lives, yet recognizing them poses challenges for conventional vision sensors due to their unique material properties, not being well perceived from RGB or depth cameras. Overcoming this limitation, thermal infrared cameras have emerged as a solution, offering improved visibility and shape information for transparent objects. In this paper, we present TRansPose, the first large-scale multispectral dataset that combines stereo RGB-D, thermal infrared (TIR) images, and object poses to promote transparent object research. The dataset includes 99 transparent objects, encompassing 43 household items, 27 recyclable trashes, 29 chemical laboratory equivalents, and 12 non-transparent objects. It comprises a vast collection of 333,819 images and 4,000,056 annotations, providing instance-level segmentation masks, ground-truth poses, and completed depth information. The data was acquired using a FLIR A65 thermal infrared (TIR) camera, two Intel RealSense L515 RGB-D cameras, and a Franka Emika Panda robot manipulator. Spanning 87 sequences, TRansPose covers various challenging real-life scenarios, including objects filled with water, diverse lighting conditions, heavy clutter, non-transparent or translucent containers, objects in plastic bags, and multi-stacked objects. TRansPose dataset can be accessed from the following link: https://sites.google.com/view/transpose-dataset